© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67298
    Prev
    Next
    INDEX
    Explanations

    `NxM` or `Nx`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     çünkü
    -1.78
    多吃
    -1.76
    の人に
    -1.57
    ==""){
    -1.57
     кул
    -1.48
    িখ
    -1.45
     baskılı
    -1.45
    adari
    -1.42
     Alquiler
    -1.41
     beſt
    -1.40
    POSITIVE LOGITS
    stwo
    1.72
     InputMaybe
    1.62
    lesssim
    1.59
     with
    1.58
    .
    1.53
     but
    1.52
     semasa
    1.48
    vább
    1.48
     Poitiers
    1.46
    즉
    1.44
    Activations Density 0.001%

    No Known Activations